Takes a string and puts it through different languages in Google Translate a requested amount of times, returning nonsense.

Overview

PythonTextObfuscator

Takes a string and puts it through different languages in Google Translate a requested amount of times, returning nonsense. Example

Requirements:

python3

For the Selenium Obfuscator:

    -Selenium
    
    -Firefox
    
    -Geckodriver

In the Selenium Obfuscator:

-The major benefit is that you can translate excel documents, the downside is that after 10 or so document translations, Google blocks your ip for a while.

-Translation is generally slower and more limited using selenium as a browser tab is being used to scrape the data. Also beware of RAM usage.

-May no longer be supported in the future due to its drawbacks.

In the Urllib Obfuscator:

-Translation is generally faster and uses very little resources as only html is downloaded through a request. Multiprocessing also allows simultanious requests and can be used to the full extent without worrying about RAM usage.

—Split by length is faster and uses less requests (better for longer texts)

—Split by newline is slower and uses more requests but adds much more translation variety.

-Reminder: Since google has a url request limit, you'll need to switch VPN locations when the request limit is hit.

    ——Don't worry too much though, as it takes quite a bit of requests to get to that point, and the block only lasts for around an hour.
You might also like...
Translate - a PyTorch Language Library

NOTE PyTorch Translate is now deprecated, please use fairseq instead. Translate - a PyTorch Language Library Translate is a library for machine transl

Auto translate textbox from Japanese to English or Indonesia
Auto translate textbox from Japanese to English or Indonesia

priconne-auto-translate Auto translate textbox from Japanese to English or Indonesia How to use Install python first, Anaconda is recommended Install

translate using your voice
translate using your voice

speech-to-text-translator Usage translate using your voice description this project makes translating a word easy, all you have to do is speak and...

translate using your voice

speech-to-text-translator Usage translate using your voice description this project makes translating a word easy, all you have to do is speak and...

This program do translate english words to portuguese

Python-Dictionary This program is used to translate english words to portuguese. Web-Scraping This program use BeautifulSoap to make web scraping, so

Translate U is capable of translating the text present in an image from one language to the other.
Translate U is capable of translating the text present in an image from one language to the other.

Translate U is capable of translating the text present in an image from one language to the other. The app uses OCR and Google translate to identify and translate across 80+ languages.

Graphical user interface for Argos Translate
Graphical user interface for Argos Translate

Argos Translate GUI Website | GitHub | PyPI Graphical user interface for Argos Translate. Install pip3 install argostranslategui

Use the state-of-the-art m2m100 to translate large data on CPU/GPU/TPU. Super Easy!
Use the state-of-the-art m2m100 to translate large data on CPU/GPU/TPU. Super Easy!

Easy-Translate is a script for translating large text files in your machine using the M2M100 models from Facebook/Meta AI. We also privide a script fo

Search for documents in a domain through Google. The objective is to extract metadata

MetaFinder - Metadata search through Google _____ __ ___________ .__ .___ / \

Comments
  • Attempt to decode JSON with unexpected mimetype: text/plain

    Attempt to decode JSON with unexpected mimetype: text/plain

    I'm not sure what's causing this, as the last time I tried this release, this issue was not present. If it's accessing content server-side, then it might be that the server has had a config change resulting in it returning a different mimetype?

    I get the error message below consistently in the console, with %2E being added to the end of the URL each time. It does seem like some translation does happen; in this case, I inputted "Test", and the URL ended with "Hlola".

    https://translate.alefvanoon.xyz/api/v1/zu/mi/Hlola%2E 0, message='Attempt to decode JSON with unexpected mimetype: text/plain; charset=utf-8', url=URL('https://translate.alefvanoon.xyz/api/v1/zu/mi/Hlola')

    From what I've gathered looking online, the issue lies in either line 13, line 469, or both.

    return (await response.json())['translation'].replace('/','⁄')

    text = (await response.json())['translation'].replace('/','⁄')

    Some of the solutions online referred to adding "content_type=None" or "content_type='text/plain'" into the brackets after "json", but this only seemed to cause further issues for me.

    opened by UltraHylia 2
  • Program Freezes Up and Looping Error

    Program Freezes Up and Looping Error

    When you have Chinese (Simplified) and/or Chinese (Traditional) enabled in the language selector, the program can freeze and an error loops in the console. It happens no matter what other languages are enabled.

    https://user-images.githubusercontent.com/60769253/197659506-38871035-e311-4710-9eb9-ac2d7387841f.mp4

    opened by DerpTaco99921 0
Releases(v0.4)
  • v0.4(Feb 2, 2022)

    Rebuilt from the ground up with a new GUI and translation method.

    Changes:

    -Improved GUI.

    -Translations are retrieved from a front-end to Google Translate called Lingva, which removes the issue with being blocked for doing too many requests.

    -Translations are done in an asynchronous function using aiohttp instead of a process pool, which is optimal for large bulk translations.

    -Removed selenium obfuscation.

    Additions: -Importing and saving text files. -Language Selector to activate or deactivate any individual language. -Language setting for the result. -Three different split methods: ____-Initial ________-Text is split by length before being passed into the obfuscate function. ________-Faster as less requests are made. ________-Different languages for each piece. ________-Tabs not preserved. ____-Continuous ________-Text is split by length inside the obfuscate function. ________-Faster as less requests are made. ________-Same languages for each piece. ________-Tabs not preserved. ____-Newline ________-Text is split by newlines and tabs. ________-Slower as more requests are made. ________-Every single line is translated with different languages. ________-Tabs preserved. -Translation Generator which creates a .csv file containing multiple translations of the same text: ____-Repeat mode obfuscates the original text each time, adding the result in each new column. ____-Continue mode obfuscates the results from each subsequent obfuscation, adding the result in each new column.

    Source code(tar.gz)
    Source code(zip)
    Python.Text.Obfuscator.v0.4.zip(15.75 KB)
  • v0.3.1c-r2(Dec 23, 2021)

  • v0.3.1c(Dec 23, 2021)

    Newlines no longer get messed up in Urllib Obfuscator. Added a choice to split by length or by newlines. —Split by length is faster and uses less requests (better for longer texts) —Split by newline is slower and uses more requests but adds much more translation variety. Reminder: Since google has a URL request limit, you'll need to switch VPN locations when the request limit is hit.

    Source code(tar.gz)
    Source code(zip)
    Python.Text.Obfuscator.v0.3.1c.zip(51.63 KB)
  • v0.3.1b(Dec 23, 2021)

  • v0.3.1a(Dec 23, 2021)

  • v0.3(Dec 23, 2021)

    I made massive improvements to the speed of the obfuscation thanks to learning about urllib.

    For example, I did translated the same ~2300 character long string of text 10 times in the old and new version; the old one took 38.8 seconds while the new one took only 6.8 seconds.

    In addition, the capacity to add a larger amount of characters is far increased as it doesn't require Firefox tabs to be open and eating up ram.

    As a test I translated the entire Among Us Wikipedia page 50 times (with a character count of over 60 thousand!), and it only took only 114 seconds to finish translating. Using the old obfuscator I wouldn't be able to translate more than half that amount, and it would take ages to complete (Like 10 mins or more).

    Unfortunately for this version the Excel Obfuscator is removed until I can figure out how to get it to work in urllib, if I can't then I'll probably add it back it with Selenium.

    At least if you couldn't get selenium to work on your computer for the previous versions you don't have to worry about getting it for this.

    Source code(tar.gz)
    Source code(zip)
    Python.Text.Obfuscator.v0.3.zip(5.73 KB)
  • v0.2.2(Dec 23, 2021)

  • v0.2.1b(Dec 23, 2021)

  • v0.2.1a(Dec 23, 2021)

    Fixed TimeoutExceptions for the string translations (textbox input) obfuscation. You can now do as many translations as you want without worrying about encountering an error. Same for amount of characters (as long as your PC can handle of course). As for excel translations they remain unchanged — since I can't do anything about Google's Document translation limit — so just switch locations on VPN like usual after 10 translations for the Excel Obfuscator.

    Source code(tar.gz)
    Source code(zip)
    Python.Text.Obfuscator.v0.2.1.zip(5.88 KB)
  • v0.2(Dec 23, 2021)

  • v0.1b(Dec 23, 2021)

  • v0.1a(Dec 23, 2021)

Source code of paper "BP-Transformer: Modelling Long-Range Context via Binary Partitioning"

BP-Transformer This repo contains the code for our paper BP-Transformer: Modeling Long-Range Context via Binary Partition Zihao Ye, Qipeng Guo, Quan G

Zihao Ye 119 Nov 14, 2022
Code for the paper "BERT Loses Patience: Fast and Robust Inference with Early Exit".

Patience-based Early Exit Code for the paper "BERT Loses Patience: Fast and Robust Inference with Early Exit". NEWS: We now have a better and tidier i

Kevin Canwen Xu 54 Jan 04, 2023
Twewy-discord-chatbot - Build a Discord AI Chatbot that Speaks like Your Favorite Character

Build a Discord AI Chatbot that Speaks like Your Favorite Character! This is a Discord AI Chatbot that uses the Microsoft DialoGPT conversational mode

Lynn Zheng 231 Dec 30, 2022
Part of Speech Tagging using Hidden Markov Model (HMM) POS Tagger and Brill Tagger

Part of Speech Tagging using Hidden Markov Model (HMM) POS Tagger and Brill Tagger In this project, our aim is to tune, compare, and contrast the perf

Chirag Daryani 0 Dec 25, 2021
Chinese segmentation library

What is loso? loso is a Chinese segmentation system written in Python. It was developed by Victor Lin ( Fang-Pen Lin 82 Jun 28, 2022

Code for Emergent Translation in Multi-Agent Communication

Emergent Translation in Multi-Agent Communication PyTorch implementation of the models described in the paper Emergent Translation in Multi-Agent Comm

Facebook Research 75 Jul 15, 2022
In this project, we compared Spanish BERT and Multilingual BERT in the Sentiment Analysis task.

Applying BERT Fine Tuning to Sentiment Classification on Amazon Reviews Abstract Sentiment analysis has made great progress in recent years, due to th

Alexander Leonardo Lique Lamas 5 Jan 03, 2022
keras implement of transformers for humans

keras implement of transformers for humans

苏剑林(Jianlin Su) 4.8k Jan 03, 2023
Voice Assistant inspired by Google Assistant, Cortana, Alexa, Siri, ...

author: @shival_gupta VoiceAI This program is an example of a simple virtual assitant It will listen to you and do accordingly It will begin with wish

Shival Gupta 1 Jan 06, 2022
GPT-Code-Clippy (GPT-CC) is an open source version of GitHub Copilot, a language model

GPT-Code-Clippy (GPT-CC) is an open source version of GitHub Copilot, a language model -- based on GPT-3, called GPT-Codex -- that is fine-tuned on publicly available code from GitHub.

Nathan Cooper 2.3k Jan 01, 2023
Implementation of the Hybrid Perception Block and Dual-Pruned Self-Attention block from the ITTR paper for Image to Image Translation using Transformers

ITTR - Pytorch Implementation of the Hybrid Perception Block (HPB) and Dual-Pruned Self-Attention (DPSA) block from the ITTR paper for Image to Image

Phil Wang 17 Dec 23, 2022
Code for the project carried out fulfilling the course requirements for Fall 2021 NLP at NYU

Introduction Fairseq(-py) is a sequence modeling toolkit that allows researchers and developers to train custom models for translation, summarization,

Sai Himal Allu 1 Apr 25, 2022
Multilingual word vectors in 78 languages

Aligning the fastText vectors of 78 languages Facebook recently open-sourced word vectors in 89 languages. However these vectors are monolingual; mean

Babylon Health 1.2k Dec 17, 2022
The first online catalogue for Arabic NLP datasets.

Masader The first online catalogue for Arabic NLP datasets. This catalogue contains 200 datasets with more than 25 metadata annotations for each datas

ARBML 94 Dec 26, 2022
Utilizing RBERT model for KLUE Relation Extraction task

RBERT for Relation Extraction task for KLUE Project Description Relation Extraction task is one of the task of Korean Language Understanding Evaluatio

snoop2head 14 Nov 15, 2022
Code for text augmentation method leveraging large-scale language models

HyperMix Code for our paper GPT3Mix and conducting classification experiments using GPT-3 prompt-based data augmentation. Getting Started Installing P

NAVER AI 47 Dec 20, 2022
🧪 Cutting-edge experimental spaCy components and features

spacy-experimental: Cutting-edge experimental spaCy components and features This package includes experimental components and features for spaCy v3.x,

Explosion 65 Dec 30, 2022
Officile code repository for "A Game-Theoretic Perspective on Risk-Sensitive Reinforcement Learning"

CvarAdversarialRL Official code repository for "A Game-Theoretic Perspective on Risk-Sensitive Reinforcement Learning". Initial setup Create a virtual

Mathieu Godbout 1 Nov 19, 2021
Text editor on python to convert english text to malayalam(Romanization/Transiteration).

Manglish Text Editor This is a simple transiteration (romanization ) program which is used to convert manglish to malayalam (converts njaan to ഞാൻ ).

Merin Rose Tom 1 May 11, 2022
skweak: A software toolkit for weak supervision applied to NLP tasks

Labelled data remains a scarce resource in many practical NLP scenarios. This is especially the case when working with resource-poor languages (or text domains), or when using task-specific labels wi

Norsk Regnesentral (Norwegian Computing Center) 850 Dec 28, 2022